Game-Theoretic Latent Space Alignment for Multi-user Semantic MIMO Communications

2026-06-10

AI Summary

This work addresses semantic mismatch in multi-user semantic MIMO communication within interference-limited cognitive radio networks, where heterogeneous latent spaces across agents impair mutual understanding and task performance. The paper introduces, for the first time, a non-cooperative game-theoretic framework for semantic alignment, jointly optimizing linear semantic MIMO transceivers under transmit power and interference constraints. By leveraging structured dimensionality reduction, the problem is transformed into a low-dimensional power allocation game, for which an iterative semantic water-filling algorithm is proposed to achieve distributed alignment. Theoretical analysis explicitly links semantic alignment with physical channel characteristics and establishes sufficient conditions for the existence, uniqueness of the Nash equilibrium, and global convergence of the algorithm. Experiments demonstrate that the proposed framework effectively balances semantic compression ratio, downstream task performance, and spectrum access efficiency, enabling robust and efficient multi-user semantic alignment.

Abstract

Semantic communications enable AI-native wireless systems by mapping raw data into compressed task-oriented latent representations. However, independently trained agents often rely on heterogeneous latent spaces and background knowledge, leading to semantic mismatch that degrades mutual understanding and downstream task execution, especially in interferencelimited multi-user wireless networks. This paper investigates distributed latent-space alignment in multi-user semantic MIMO interference networks with cognitive radio constraints. We consider primary users and semantic-aware secondary users sharing the same wireless resources, where secondary agents must simultaneously mitigate interference and align heterogeneous semantic representations. To address this problem, we formulate semantic alignment as a non-cooperative game and derive a closed-form solution for the joint optimization of linear semantic MIMO transceivers under power and interference constraints. Exploiting the structure of the problem, we recast the original matrix valued optimization into a lower-dimensional power-allocation game, leading to an iterative semantic water-filling algorithm. We establish sufficient conditions for existence, uniqueness, and global convergence to a Nash equilibrium, explicitly relating semantic alignment properties and physical-channel interactions. Numerical results assess the performance of the proposed framework, revealing key trade-offs among semantic compression, task performance, and hierarchical spectrum access.

Problem

• semantic communications
• latent space alignment
• multi-user MIMO
• interference networks
• cognitive radio

Innovation

• semantic communications
• latent space alignment
• game theory
• semantic MIMO
• cognitive radio